A Comparison of Contemporary Methods on Univariate Time Series Forecasting

Abstract

In data science, time series forecasting is the process of utilizing past or present (known) observations of a target variable to make predictions about future (unknown) observations. Due to the usefulness of forecasting applications in numerous real-life problems, various Statistical and Machine Learning forecasting models have been proposed over recent years. The purpose of this chapter is to compare the performance of several contemporary forecasting models that are considered state of the art. These include Autoregressive Integrated Moving Average (ARIMA), Neural Basis Expansion Analysis (NBEATS), Probabilistic Time Series Modeling focusing on deep learning-based models and others. In the first section of this work a brief theoretical background of the methods is provided. Then, the experimental procedure is being described. For the comparison, 40 univariate time series of financial data that cover a 1-year period were used. A python repository of automated time series forecasting models (AtsPy) was exploited to run the experiments. For the final comparison three different metrics (RMSE, MAE and MAPE) were taken into consideration. The results of this extended experimental procedure are presented through various explanatory diagrams of the methods' performance in the final section.

Cloud-Based Accounting Information Systems and Financial Reporting Quality of Listed Information and Communication Technology Firms in Nigeria

“…These systems leverage remote servers, advanced software, and internet connectivity to store, process, and analyze financial data without onpremise installations. Offering features like general ledger management, accounts receivable and payable, financial reporting, and budgeting accessible via web browsers or mobile apps, cloud-based AIS provide scalability, enabling organizations to adjust resources according to needs, reducing infrastructure costs (Karanikola et al, 2023). They offer real-time access and collaboration, enhancing productivity, and incorporate advanced security measures like encryption and access controls to protect sensitive data and ensure compliance.…”

Investigating Deep Stock Market Forecasting with Sentiment Analysis

“…According to the implementation of more than 38000 models, it is argued that the architectures of LSTMs and CNNs outperform all others. In [30], the comparison of a number of methods-such as ARIMA, neural basis expansion analysis (NBEATS), and probabilistic methods based on deep learning models-applied to time series of financial data is presented. Additionally, in [31], a comparison between CNNs, LSTMs, and a hybrid model of them is given, which was deployed on data concerning the forecasting of the energy load coming from photovoltaics.…”

Forecasting Marine Heatwaves using Machine Learning

“…To summarise, the overall design consists of two stacks, with the trend stack being accompanied by the seasonality stack (Oreshkin et al, 2020), as well as a double residual stacking topology mixed with the forecast-backcast principle. When comparing the performances of different univariate time-series forecasting methods, such as in financial data forecasting, N-BEATS has been found to be one of the best performing models (Karanikola et al, 2022). In our model, we used 8 layers, 12 stacks, 180 lags and trained up to 100 epochs.…”